System and method for multi-channel speech privacy processing
AssigneeMicrosoft Technology Licensing, LLC
InventorDushyant SHARMA
Life of this patent
Estimating the term…
Abstract
A method, computer program product, and computing system for receiving a speech signal from a single microphone. A sensitive speech component is identified from the speech signal. In response to identifying the sensitive speech component, a filtered speech signal is generated by removing the sensitive speech component from the speech signal. A voice style transfer of the speech signal is generated. Speech processing is performed on the filtered speech signal and the voice style transfer of the speech signal.
Claims20
A method comprising:
- receiving, by a speech processing system, a speech signal containing voice characteristics of a user;
- generating, from the speech signal, training data for an automatic speech recognition (ASR) model by filtering the speech signal to obtain a filtered speech signal and generating a synthetic speech signal from a transcription of the speech signal, the training data including both the filtered speech signal and the synthetic speech signal, wherein the voice characteristics of the user are anonymized in both the filtered speech signal and the synthetic speech signal;
- and
- outputting the training data to a device, the training data being used to train the ASR model to perform speech recognition.
A system comprising:
- a processor;
- and
- a memory storing programming instructions for execution by the processor, the programming instructions, upon execution by the processor, causing the system to perform the following operations:
- receiving, by a speech processing system, a speech signal containing voice characteristics of a user;
- generating, from the speech signal, training data for an automatic speech recognition (ASR) model by filtering the speech signal to obtain a filtered speech signal and generating a synthetic speech signal from a transcription of the speech signal, the training data including both the filtered speech signal and the synthetic speech signal, wherein the voice characteristics of the user are anonymized in both the filtered speech signal and the synthetic speech signal;
- and
- outputting the training data to a device, the training data being used to train the ASR model to perform speech recognition.
A computer program product storing programming instructions for execution by a processor of a system, the programming instructions, upon execution by the processor, causing the system to perform the following operations:
- receiving, by a speech processing system, a speech signal containing voice characteristics of a user;
- generating, from the speech signal, training data for an automatic speech recognition (ASR) model by filtering the speech signal to obtain a filtered speech signal and generating a synthetic speech signal from a transcription of the speech signal, the training data including both the filtered speech signal and the synthetic speech signal, wherein the voice characteristics of the user are anonymized in both the filtered speech signal and the synthetic speech signal;
- and
- outputting the training data to a device, the training data being used to train the ASR model to perform speech recognition.
Dependencies are inferred from the claim text.